A Big Data approach for battery electrolytes

A new paper outlines a path for AI and machine learning to help build tomorrow’s batteries

2025-05-05

(Press-News.org) Discovering new, powerful electrolytes is one of the major bottlenecks for designing next-generation batteries for electric vehicles, phones, laptops and grid-scale energy storage.

The most stable electrolytes are not always the most conductive. The most efficient batteries are not always the most stable. And so on.

“The electrodes have to satisfy very different properties at the same time. They always conflict with each other,” said Ritesh Kumar, an Eric and Wendy Schimdt AI in Science Postdoctoral Fellow working in the Amanchukwu Lab at the University of Chicago Pritzker School of Molecular Engineering (UChicago PME).

Kumar is the first author of a new paper published in Chemistry of Materials that is putting artificial intelligence and machine learning on the job. The paper outlines a new framework for finding molecules that maximize three components that make an ideal battery electrolyte – ionic conductivity, oxidative stability and Coulombic efficiency.

Pulling from a dataset compiled from 250 research papers going back to the earliest days of lithium-ion battery research, the group used AI to tally what they call the “eScore” for different molecules. The eScore balances those three criteria, identifying molecules that check all three boxes.

“The champion molecule in one property is not the champion molecule in another,” said Kumar’s principal investigator, UChicago PME Neubauer Family Assistant Professor of Molecular Engineering Chibueze Amanchukwu.

They’ve already tested their process, using AI to identify one molecule that performs as well as the best electrolytes on the market, a major advance in a field that often relies on trial-and-error.

“Electrolyte optimization is a slow and challenging process where researchers frequently resort to trial-and-error to balance competing properties in multi-component mixtures,” said Northwestern University Assistant Professor of Chemical and Biological Engineering Jeffrey Lopez, who was not involved in the research. “These types of data-driven research frameworks are critical to help accelerate the development of new battery materials and to leverage advancements in AI-enabled science and laboratory automation.”

The music of batteries

Artificial intelligence spots promising candidates for scientists to test in the lab so they waste less time, energy and resources on dead ends and false starts. UChicago PME researchers are already using AI to help develop cancer treatments, immunotherapies, water treatment methods, quantum materials and other new technologies.

Given that the theoretical number of molecules that could make battery electrolytes is 10 to the 60th power, or a one with 60 zeroes after it, technology that can flag likely winners from billions of non-starters gives researchers a huge advantage.

“It would have been impossible for us to go through hundreds of millions of compounds to say, ‘Oh, I think we should study this one,’” Amanchukwu said.

Amanchukwu compared using AI in research to listening to music online.

Imagine an AI trained on a particular person’s musical taste, the combination of qualities that go into their own personal “eScore” for good songs. The new electrolyte research created the equivalent of an AI that can go through an existing playlist and, song by song, predict whether the person will like it. The next step will be an AI that can create a playlist of songs it thinks the person will like, a subtle but important conceptual tweak.

The final step – and the goal of the Amanchukwu Lab’s AI research – will be an AI that can write the music, or in this case design a new molecule, that meets all the parameters given.

Amanchukwu last year received a Google Research Scholar Award to help the lab get closer to that final step: truly generative electrolyte AI.

A quirk of graphic design

The team started curating the training data for the AI manually starting in 2020.

“The current dataset has thousands of potential electrolytes which we extracted from literature that spanned over 50 years of research,” Kumar said.

One of the reasons they have to enter the data manually comes not from chemistry, but from graphic design.

When researchers write papers and journals lay them out in magazine format, the numbers the team turns into eScores are typically found in images. These are the jpeg or .png illustrations, charts, diagrams and other graphics that run within the text, but are not part of the text itself.

Most large language models training with research papers just read the text, meaning the UChicago PME team will be manually entering training data for some time to come.

“Even the models today really struggle with extracting data from images,” Amanchukwu said.

Although the training data is massive, it’s only the first step.

“I don't want to find a molecule that was already in my training data,” Amanchukwu said. “I want to look for molecules in very different chemical spaces. So we tested how well these models predict when they see a molecule that they've never seen before.”

The team found that when a molecule was chemically similar to one from the training data, the AI predicted how good of an electrolyte it would make with high accuracy. It struggled to flag unfamiliar materials, marking the team’s next challenge in the quest to use AI to design next-generation batteries.

Citation: “Electrolytomics: A Unified Big Data Approach for Electrolyte Design and Discovery,” Kumar et al, Chemistry of Materials, April 1, 2025. DOI: 10.1021/acs.chemmater.4c03196

END

ELSE PRESS RELEASES FROM THIS DATE:

Moffitt study finds structural barriers may prevent cancer care for people living with HIV

2025-05-05

TAMPA, Fla. (May 5, 2025) — People living with HIV are less likely to receive potentially lifesaving cancer treatment if they live in communities with lower income levels and educational attainment, according to a new national study led by researchers from Moffitt Cancer Center. In the study, published in Cancer, researchers looked at cancer treatment records for more than 31,000 adults with HIV who were diagnosed with one of 14 common cancers between 2004 and 2020. They found that 16.5% of them did not receive the recommended first line curative treatment for ...

Min proteins for max efficiency during cell division

2025-05-05

The Min protein system prevents abnormal cell division in bacteria by forming oscillating patterns between the ends of a cell (“poles”). Despite decades of theoretical work, predicting the protein concentrations at which oscillations start and whether cells can maintain them under different conditions has been a challenge. Understanding these thresholds is important because they reveal how efficient this self-organizing system is in guiding division to the right place. UC San Diego researchers have engineered ...

How tiny particles coordinate energy transfer inside cells uncovered

2025-05-05

Protons are the basis of bioenergetics. We know them, in our everyday life, from the pH values we see on various soaps and lotions. But the ability to move them through biological systems is essential for life. A new study shows for the first time that proton transfer is directly influenced by the spin of electrons, when measured in chiral biological environments such as proteins. In other words, proton movement in living systems is not purely chemical; it is also a quantum process involving electron spin and molecular chirality. The quantum process directly affects ...

Gorilla study reveals complex pros and cons of friendship

2025-05-05

Friendship comes with complex pros and cons – possibly explaining why some individuals are less sociable, according to a new study of gorillas. Scientists examined over 20 years of data on 164 wild mountain gorillas, to see how their social lives affected their health. Costs and benefits changed depending on the size of gorilla groups, and differed for males and females. For example, friendly females in small groups didn’t get ill very often but had fewer offspring – while those in large groups got ill more but had higher birth rates. Meanwhile, males with strong social bonds tended to get ill more – ...

Ancient Andes society used hallucinogens to strengthen social order

2025-05-05

Two thousand years before the Inca empire dominated the Andes, a lesser-known society known as the Chavín Phenomenon shared common art, architecture, and materials throughout modern-day Peru. Through agricultural innovations, craft production, and trade, Chavín shaped a growing social order and laid the foundations for hierarchical society among the high peaks. But one of their most powerful tools wasn’t farming. It was access to altered states of consciousness. That’s according to a new study that uncovered the earliest-known direct evidence of the use of psychoactive plants in the Peruvian Andes. A team ...

Biological ‘clocks’ key to muscle health and accelerated ageing in shift workers

2025-05-05

Muscle cells contain their own circadian clocks and disrupting them with shift work can have a profound impact on ageing, according to new research. A study published today in Proceedings of the National Academy of Sciences (PNAS) contributes to the growing evidence of the damage shift work has on health. The King’s College London team revealed how muscle cells have an intrinsic timekeeping mechanism that regulates protein turnover, modulating muscle growth and function. At night, the muscle clock activates the breakdown of defective proteins, replenishing muscles while the body rests. Altering this intrinsic ...

Physical cloaking works like a disappearing act for structural defects

2025-05-05

Whether designing a window in an airliner or a cable conduit for an engine, manufacturers devote a lot of effort to reinforcing openings for structural integrity. But the reinforcement is rarely perfect and often creates structural weaknesses elsewhere. Now, engineers at Princeton and Georgia Institute of Technology have developed a technique that can maintain structural integrity by essentially hiding the opening from the surrounding forces. Rather than reinforcing the opening to protect against a few select forces, the new approach reorganizes nearly any set of forces that could affect the surrounding material to avoid the opening. In a May 5 article in the ...

New molecular label could lead to simpler, faster tuberculosis tests

2025-05-05

CAMBRIDGE, MA -- Tuberculosis, the world’s deadliest infectious disease, is estimated to infect around 10 million people each year, and kills more than 1 million annually. Once established in the lungs, the bacteria’s thick cell wall helps it to fight off the host immune system. Much of that cell wall is made from complex sugar molecules known as glycans, but it’s not well-understood how those glycans help to defend the bacteria. One reason for that is that there hasn’t been an easy way to label them inside cells. MIT chemists have now overcome that obstacle, demonstrating that they can label a ...

How are they biting? High speed video reveals unexpected jaw movements in reef fish

2025-05-05

Some reef fish have the unexpected ability to move their jaws from side to side, biologists at the University of California, Davis have discovered. This ability – which is rare among vertebrate animals – allows these fish to feed rapidly and efficiently on algae growing on rocks. The work is published May 5 in Proceedings of the National Academy of Sciences. Being able to move your jaw from side to side might not seem surprising from a human point of view, but if you look across all vertebrate ...

Targeting gluten: researchers delete proteins in wheat harmful to people with celiac disease

2025-05-05

Wheat is a major source of calories, carbohydrates and protein worldwide, and its distinctive gluten proteins are what gives bread and pasta dough texture and elasticity. But it also can cause autoimmune reactions such as celiac disease, which is growing in prevalence worldwide. Researchers at the University of California, Davis, have deleted a cluster of genes in wheat that generates gluten proteins that can trigger immune reactions without harming the breadmaking quality of this globally nutritious crop. The findings, published this month in the journal Theoretical and Applied Genetics, won’t ...

A Big Data approach for battery electrolytes

ELSE PRESS RELEASES FROM THIS DATE:

LAST 30 PRESS RELEASES: